CN110618754B - Surface electromyogram signal-based gesture recognition method and gesture recognition armband - Google Patents
Surface electromyogram signal-based gesture recognition method and gesture recognition armband Download PDFInfo
- Publication number
- CN110618754B CN110618754B CN201910812434.4A CN201910812434A CN110618754B CN 110618754 B CN110618754 B CN 110618754B CN 201910812434 A CN201910812434 A CN 201910812434A CN 110618754 B CN110618754 B CN 110618754B
- Authority
- CN
- China
- Prior art keywords
- gesture
- signal
- gesture recognition
- signals
- surface electromyographic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2203/00—Indexing scheme relating to G06F3/00 - G06F3/048
- G06F2203/01—Indexing scheme relating to G06F3/01
- G06F2203/011—Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns
Abstract
The invention discloses a gesture recognition method and a gesture recognition arm band based on surface electromyographic signals, wherein the method comprises the steps of collecting multi-channel surface electromyographic signals of each reference gesture, respectively extracting and coding the characteristics of each surface electromyographic signal to obtain a characteristic vector corresponding to each reference gesture, acquiring the characteristic vector of a specific gesture by adopting the same method when gesture recognition is needed, and calculating the similarity between the characteristic vector and each reference gesture characteristic vector so as to perform gesture recognition. According to the invention, the accuracy of gesture recognition is improved by extracting features of the surface electromyographic signals of a plurality of positions.
Description
Technical Field
The invention belongs to the technical field of gesture recognition, and particularly relates to a gesture recognition method and a gesture recognition arm band based on surface electromyogram signals.
Background
The gesture recognition has important application values in the aspects of man-machine interaction, sign language recognition, medical diagnosis, remote education, action capture and the like. Most gesture recognition devices are implemented based on computer vision, and the sensor used is a camera. This approach has several disadvantages: firstly, gesture recognition is limited by the visual field of a camera, and when the part of a hand is shielded or the ambient light is poor, the recognition effect is poor; secondly, the difficulty in identifying micro actions is high, the effect of identifying some unobvious limb actions is poor, and small-amplitude fine actions cannot be identified; third, for people with disabled hands or fingers, the intention of the action cannot be captured visually. Other approaches to gesture recognition have been explored in the industry.
The MYO wristband (gesture control armlet) is an armlet proposed by Thalmic Labs of the canadian startup company, and adopts a pattern recognition method of body surface muscle electrical signals to judge actions. The MYO wrist strap can be worn above the elbow joint of any arm to detect the electrical activity generated by the muscle of the user, and is wirelessly connected with other electronic products through a low-power Bluetooth device to realize gesture control. The MYO wristband has the following disadvantages: firstly, the MYO wrist strap uses metal electrodes in terms of structure, and is integrally of a hard plastic structure, so that the MYO wrist strap is not comfortable to wear after being attached to the skin for a long time; secondly, the MYO wrist strap is poor in portability from the use angle, calibration training needs to be carried out before each use, and the actual use is still somewhat cumbersome; thirdly, the accuracy of a simple EMG electromyographic signal is not high, the noise is large and the measuring point is not in a simple ring shape; fourthly, the MYO wrist strap cannot be subjected to proportional control, only the characteristics of the action are extracted to form a state space, then when the signal comes in, the characteristic of the signal is judged to be close to a certain state, and the accuracy of gesture recognition needs to be improved.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a gesture recognition method and a gesture recognition arm band based on surface electromyographic signals.
In order to achieve the above object, the gesture recognition method based on surface electromyogram signal of the present invention comprises the following steps:
s1: setting N reference gestures according to requirements, sequentially making each reference gesture by personnel, and collecting surface electromyographic signals S at different positions of an arm by adopting K surface electromyographic signal sensors in the action process of each reference gesturen,k，n＝1,2,…,N，k＝1,2,…,K；
S2: for each surface electromyographic signal Sn,kRespectively extracting the features fn,kThe feature type can be set as required; for each feature fn,kCoding to obtain corresponding code value dn,kSo as to obtain the feature vector D of each reference gesturen＝(dn,1,dn,2,…,dn,K)；
S3: when gesture recognition is needed, a person carries out a specific gesture action, and in the process, according to the position of the surface electromyographic signal sensor at the time of acquiring the reference gesture, K surface electromyographic signal sensors are adopted to acquire the surface electromyographic signal S 'at the corresponding positions of the arm'k；
S4: for each surface electromyogram signal S'kRespectively extracting to obtain the characteristic f'kAnd for each feature f'kTo carry outCoding to obtain corresponding coded value d'kTo obtain a feature vector D ' ═ D ' of the specific gesture '1,d′2,…,d′K)；
S5: calculating a feature vector D ' ═ D ' of the specific gesture respectively '1,d′2,…,d′K) And feature vectors D of N reference gesturesn＝(dn,1,dn,2,…,dn,K) Similarity between RkScreening out the maximum similarity RmaxIf the maximum similarity R ismaxIf the specific gesture is greater than the preset threshold, the specific gesture is judged to be the maximum similarity RmaxAnd if the corresponding reference gesture is not one of the K reference gestures, the gesture recognition fails, and the collection of the specific gesture is prompted to be carried out again.
The invention also provides a gesture recognition armband based on the surface electromyogram signal, which comprises an armband base layer, N surface electromyogram signal sensors, N signal conditioning modules, a main control module and a power supply module, wherein:
the arm belt base layer adopts a piece of flexible fabric with a stretching function, one side of the flexible fabric, which is in contact with the skin, is a back side, and the other side of the flexible fabric is a front side;
the N surface electromyographic signal sensors are distributed and installed on the front surface of the arm back base layer, and electrodes of the N surface electromyographic signal sensors extend to the back surface of the arm band base layer and are used for collecting surface electromyographic signals and sending the surface electromyographic signals to corresponding signal conditioning modules;
the N signal conditioning modules are distributed on the front surface of the arm back base layer and used for respectively conditioning the received surface electromyographic signals and sending the obtained surface electromyographic signals to the main control module;
the main control module is installed on the front surface of the arm back base layer and comprises two working modes: a training mode and a recognition mode, wherein when the device works in the training mode, a feature vector acquisition method of a reference gesture in the gesture recognition method based on the surface electromyogram signal of claim 1 is adopted to obtain a feature vector of each reference gesture; when the surface electromyogram signal-based gesture recognition method works in a recognition mode, a feature vector acquisition method of a specific gesture in the surface electromyogram signal-based gesture recognition method of claim 1 is adopted to obtain a feature vector of the specific gesture, and the similarity between the feature vector of the specific gesture and the feature vector of each reference gesture is calculated to realize gesture recognition; when the gesture recognition is successful, generating a corresponding control instruction according to the recognized reference gesture and wirelessly sending the control instruction to a control object, and when the gesture recognition is failed, prompting to perform specific gesture collection again;
the power supply module is arranged on the front surface of the arm back base layer and used for supplying power to the N surface electromyographic signal sensors 2, the N signal conditioning modules and the main control module.
The invention relates to a gesture recognition method and a gesture recognition arm band based on surface electromyographic signals, which are used for acquiring multi-channel surface electromyographic signals of each reference gesture, respectively extracting and coding the characteristics of each surface electromyographic signal to obtain a characteristic vector corresponding to each reference gesture, and when gesture recognition is required, acquiring the characteristic vector of a specific gesture by adopting the same method, and calculating the similarity between the characteristic vector and each reference gesture characteristic vector so as to perform gesture recognition. According to the invention, the accuracy of gesture recognition is improved by extracting features of the surface electromyographic signals of a plurality of positions.
Drawings
FIG. 1 is a flowchart of an embodiment of a gesture recognition method based on a surface electromyogram signal according to the present invention;
fig. 2 is a flowchart of an average energy-based code value determination method in the present embodiment;
FIG. 3 is a structural diagram of a gesture recognition arm band based on surface electromyogram signals according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided in order to better understand the present invention for those skilled in the art with reference to the accompanying drawings. It is to be expressly noted that in the following description, a detailed description of known functions and designs will be omitted when it may obscure the subject matter of the present invention.
Examples
Fig. 1 is a flowchart of a specific embodiment of a gesture recognition method based on a surface electromyogram signal according to the present invention. As shown in fig. 1, the gesture recognition method based on the surface electromyogram signal of the present invention specifically includes the following steps:
s101: acquiring a reference gesture surface electromyographic signal:
setting N reference gestures according to requirements, sequentially making each reference gesture by personnel, and collecting surface electromyographic signals S at different positions of an arm by adopting K surface electromyographic signal sensors in the action process of each reference gesturen,k，n＝1,2,…,N，k＝1,2,…,K。
In practical application, a plurality of groups of surface electromyographic signals can be collected for each reference gesture, the surface electromyographic signals collected by the electromyographic signal sensors are averaged, and the obtained average surface electromyography is used as the surface electromyographic signal Sn,k. This reduces the effect of noise on acquisition.
S102: acquiring a reference gesture feature vector:
for each surface electromyographic signal Sn,kRespectively extracting the features fn,kThe feature type may be set as desired. For each feature fn,kCoding to obtain corresponding code value dn,kSo as to obtain the feature vector D of each reference gesturen＝(dn,1,dn,2,…,dn,K)。
The reference gesture in this embodiment includes 6 types: fist making, palm stretching, wrist bending, wrist stretching, wrist bending on the side of the ulna, and double-click of thumb and middle finger. Set surface electromyographic signal Sn,kIs characterized by a surface electromyographic signal Sn,kThe average energy of (2). In the embodiment, three threshold values A, B, C are designed, and C > B > A > 0, wherein the threshold value A is used for judging whether the surface electromyographic signal sensor obviously detects the electromyographic signal, and the characteristic fn,kIf the surface electromyographic signal sensor detects a surface electromyographic signal, the threshold value A is lower than the threshold value A, the surface electromyographic signal sensor is judged not to detect a corresponding signal, the threshold value B is used for judging whether the surface electromyographic signal sensor detects a stronger surface electromyographic signal, and the characteristic fn,kAbove the threshold B, the surface electromyographic signal sensor is considered to detect a strong signal, and the characteristic fn,kThe surface electromyogram signal sensor is considered to detect a signal with normal intensity between a threshold value A and a threshold value B, and a threshold value C is setThe value far larger than the threshold value B indicates that the average energy value of the collected surface electromyogram signals of the surface electromyogram signal sensing sensor exceeds the normal range, which indicates that the collected surface electromyogram signals are abnormal (for example, a large amount of noise is mixed). The three thresholds may be set based on empirical values.
The average energy is judged through the three threshold values, so that the characteristic f is judgedn,kCoding to obtain surface electromyographic signals Sn,kThe feature vector of (2). Fig. 2 is a flowchart of the average energy-based code value determination method in the present embodiment. As shown in fig. 2, the specific steps of the average energy-based code value determining method in this embodiment include:
s201: extracting average energy characteristics:
setting a sliding window with the length L, sliding on the data sequence of the surface electromyogram signal by a sliding step length lambda, lambda is less than L, thereby dividing the surface electromyogram signal into P subsignals spWherein P is 1,2, …, P. That is, there is a partial overlap of two adjacent sub-signals. Calculating each sub-signal spAverage energy e ofpP mean energies epI.e. as a characteristic of the surface electromyographic signal.
S202: average energy ordering:
p sub-signals s of the surface electromyography signalpAverage energy e ofpAnd sequencing from large to small to obtain an average energy sequence.
S203: the number of initial evaluations t is 1.
S204: calculating the average energy mean value:
selecting the t-th to Q + t-th average energies in the average energy sequence, and calculating to obtain an average energy mean value
Q is set according to actual needs.
S205: judging whether to use
If yes, go to step S206, otherwise go to stepStep S207.
S206: determining an encoding value based on a threshold:
acquiring a coding value d corresponding to the surface electromyogram signal by adopting the following formula:
and finishing the coding.
S207: judging whether t is less than tmax，tmaxRepresents the maximum number of evaluations, obviously tmaxP-Q is not more than P-Q. If t < tmaxThe process proceeds to step S208, otherwise, the process proceeds to step S209.
S208: let t be t +1, return to step S204.
S209: and (5) making the coded value d of the surface electromyogram signal be omega, and omega be a preset negative constant, and finishing coding.
In the embodiment, the average energy-based feature vector extraction method adopts multiple evaluations on the average energy mean value, so that coding errors caused by noise can be effectively avoided. Assuming that there are 8 surface myoelectric signal sensors in this embodiment, the resulting eigenvector includes 8 encoded values, e.g., 00110N21, where N is used to denote the preset negative constant ω.
S103: collecting the surface electromyographic signals of specific gestures:
when gesture recognition is needed, a person carries out a specific gesture action, and in the process, according to the position of the surface electromyographic signal sensor at the time of acquiring the reference gesture, K surface electromyographic signal sensors are adopted to acquire the surface electromyographic signal S 'at the corresponding positions of the arm'k。
S104: acquiring a specific gesture feature vector:
for each surface electromyogram signal S'kRespectively extracting to obtain the characteristic f'kAnd for each feature f'kCoding is carried out to obtain a corresponding coded value d'kTo obtain a feature vector D ' ═ D ' of the specific gesture '1,d′2,…,d′K)。
S105: gesture matching:
calculating a feature vector D ' ═ D ' of the specific gesture respectively '1,d′2,…,d′K) And feature vectors D of N reference gesturesn＝(dn,1,dn,2,…,dn,K) Similarity between RkScreening out the maximum similarity RmaxIf the maximum similarity R ismaxIf the specific gesture is greater than the preset threshold, the specific gesture is judged to be the maximum similarity RmaxAnd if not, the specific gesture is not considered to be one of the N reference gestures, the gesture recognition fails, and the specific gesture collection is prompted to be carried out again.
In order to realize the gesture recognition method based on the surface electromyogram signal, the invention also provides a gesture recognition arm band based on the surface electromyogram signal. FIG. 3 is a structural diagram of a gesture recognition arm band based on surface electromyogram signals according to an embodiment of the present invention. As shown in fig. 3, the gesture recognition armband based on the surface electromyogram signal in the invention comprises an armband base layer 1, N surface electromyogram signal sensors 2, N signal conditioning modules 3, a main control module 4 and a power supply module 5.
The arm band base layer 1 adopts a piece of flexible fabric with a stretching function, one side of the flexible fabric, which is in contact with the skin, is a back side, and the other side of the flexible fabric is a front side. In order to facilitate wearing, the opposite-inserting type lock catches can be arranged at the two ends of the armband base layer 1, and the armband is fixed when being worn.
The N surface electromyographic signal sensors 2 are distributed on the front surface of the arm back base layer 1, and electrodes of the surface electromyographic signal sensors extend to the back surface of the arm band base layer 1 and are used for collecting surface electromyographic signals and sending the surface electromyographic signals to the corresponding signal conditioning modules 3.
The N signal conditioning modules 3 are distributed on the front surface of the arm back base layer 1, and are configured to perform signal conditioning on the received surface electromyogram signals, generally including amplification and denoising, and send the obtained surface electromyogram signals to the main control module 4.
The main control module 4 is installed on the front surface of the arm back base layer 1 and comprises two working modes: when the gesture recognition method works in the training mode, the feature vector of each reference gesture is obtained by adopting the feature vector acquisition method of the reference gesture in the gesture recognition method based on the surface electromyogram signal; when the gesture recognition method works in a recognition mode, the feature vector of the specific gesture is obtained by adopting the feature vector acquisition method of the specific gesture in the gesture recognition method based on the surface electromyogram signal, and the similarity between the feature vector of the specific gesture and the feature vector of each reference gesture is calculated to realize gesture recognition; when the gesture recognition is successful, a corresponding control instruction is generated according to the recognized reference gesture and is wirelessly sent to a control object, when the gesture recognition is failed, specific gesture collection is prompted again, voice prompt can be adopted, an indicator lamp or a display screen can be configured on the main control module 4, and light, characters or patterns are adopted for prompting.
The power supply module 5 is installed on the front surface of the arm back base layer 1 and used for supplying power to the N surface electromyographic signal sensors 2, the N signal conditioning modules 3 and the main control module 4.
In order to increase the difference between the reference gestures and expand the number of the reference gestures to expand the application scene, an inertial sensor 6 may be further added to the main control module 4 for acquiring an inertial signal and sending the inertial signal to the main control module 4. When the main control module 4 works in a training mode, the angle of the inertial signal is extracted and used as the characteristic of a certain reference gesture; when the main control module 4 works in the recognition mode, firstly, the angle of an inertial signal acquired by a specific gesture is extracted, the angle difference between the inertial signal and each reference gesture with the angle characteristics as characteristics is calculated respectively, the minimum angle difference is screened out, if the minimum angle difference is smaller than a preset threshold value, the specific gesture is judged to be the reference gesture corresponding to the minimum angle difference, the gesture recognition is successful, otherwise, the gesture recognition based on the inertial signal fails, and then the gesture recognition is carried out based on the surface electromyographic signal.
Although illustrative embodiments of the present invention have been described above to facilitate the understanding of the present invention by those skilled in the art, it should be understood that the present invention is not limited to the scope of the embodiments, and various changes may be made apparent to those skilled in the art as long as they are within the spirit and scope of the present invention as defined and defined by the appended claims, and all matters of the invention which utilize the inventive concepts are protected.
Claims (3)
1. A gesture recognition method based on surface electromyogram signals is characterized by comprising the following steps:
s1: setting N reference gestures according to requirements, sequentially making each reference gesture by personnel, and collecting surface electromyographic signals S at different positions of an arm by adopting a K surface electromyographic signal sensor in the action process of each reference gesturen,k，n＝1,2,…,N，k＝1,2,…,K；
S2: for each surface electromyographic signal Sn,kRespectively extracting the features fn,kThe feature type can be set as required; for each feature fn,kCoding to obtain corresponding code value dn,kSo as to obtain the feature vector D of each reference gesturen＝(dn,1,dn,2,…,dn,K) (ii) a Wherein the encoded value of the surface electromyography signal is determined based on the mean energy, comprising the steps of:
s2.1: setting a sliding window with the length L, sliding on the data sequence of the surface electromyogram signal by a sliding step length lambda, lambda is less than L, thereby dividing the surface electromyogram signal into P subsignals spWherein P is 1,2, …, P; calculating each sub-signal spAverage energy e ofpP mean energies epI.e. as a characteristic of surface electromyographic signals;
s2.2: p sub-signals s of the surface electromyography signalpAverage energy e ofpSequencing from big to small to obtain an average energy sequence;
s2.3: initializing the evaluation times t as 1;
s2.4: selecting the t-th to Q + t-th average energies in the average energy sequence, and calculating to obtain an average energy mean value
Q is set according to actual needs;
s2.5: judging whether to use
If yes, entering the stepStep S2.6, otherwise, step S2.7 is carried out;
s2.6: acquiring a coding value d corresponding to the surface electromyogram signal by adopting the following formula:
ending the encoding;
s2.7: judging whether t is less than tmax，tmaxRepresents the maximum number of evaluations if t < tmaxStep S2.8 is entered, otherwise step S2.9 is entered;
s2.8: making t equal to t +1, and returning to the step S2.4;
s2.9: making the coded value d of the surface electromyogram signal equal to omega, wherein omega is a preset negative constant, and finishing coding;
s3: when gesture recognition is needed, a person carries out a specific gesture action, and in the process, according to the position of the surface electromyographic signal sensor at the time of acquiring the reference gesture, K surface electromyographic signal sensors are adopted to acquire the surface electromyographic signal S 'at the corresponding positions of the arm'k；
S4: for each surface electromyogram signal S'kRespectively extracting to obtain the characteristic f'kAnd for each feature f'kCoding is carried out to obtain a corresponding coded value d'kTo obtain a feature vector D ' ═ D ' of the specific gesture '1,d′2,…,d′K)；
S5: calculating a feature vector D ' ═ D ' of the specific gesture respectively '1,d′2,…,d′K) And feature vectors D of N reference gesturesn＝(dn,1,dn,2,…,dn,K) Similarity between RkScreening out the maximum similarity RmaxIf the maximum similarity R ismaxIf the specific gesture is greater than the preset threshold, the specific gesture is judged to be the maximum similarity RmaxAnd if the corresponding reference gesture is not one of the K reference gestures, the gesture recognition fails, and the collection of the specific gesture is prompted to be carried out again.
2. The utility model provides a gesture recognition armlet based on surface electromyogram signal which characterized in that, includes armlet basic unit, N surface electromyogram signal sensor, N signal conditioning module, host system and power module, wherein:
the arm belt base layer adopts a piece of flexible fabric with a stretching function, one side of the flexible fabric, which is in contact with the skin, is a back side, and the other side of the flexible fabric is a front side;
the N surface electromyographic signal sensors are distributed and installed on the front surface of the arm back base layer, and electrodes of the N surface electromyographic signal sensors extend to the back surface of the arm belt back base layer and are used for collecting surface electromyographic signals and sending the surface electromyographic signals to corresponding signal conditioning modules;
the N signal conditioning modules are distributed on the front surface of the arm back base layer and used for respectively conditioning the received surface electromyographic signals and sending the obtained surface electromyographic signals to the main control module;
the main control module is installed on the front surface of the arm back base layer and comprises two working modes: a training mode and a recognition mode, wherein when the device works in the training mode, a feature vector acquisition method of a reference gesture in the gesture recognition method based on the surface electromyogram signal of claim 1 is adopted to obtain a feature vector of each reference gesture; when the surface electromyogram signal-based gesture recognition method works in a recognition mode, a feature vector acquisition method of a feature gesture in the surface electromyogram signal-based gesture recognition method of claim 1 is adopted to obtain a feature vector of a specific gesture, and the similarity between the feature vector of the specific gesture and the feature vector of each reference gesture is calculated to realize gesture recognition; when the gesture recognition is successful, generating a corresponding control instruction according to the recognized reference gesture and wirelessly sending the control instruction to a control object, and when the gesture recognition is failed, prompting to perform specific gesture collection again;
the power supply module is arranged on the front surface of the arm back base layer and used for supplying power to the N surface electromyographic signal sensors 2, the N signal conditioning modules and the main control module.
3. The gesture recognition armband of claim 2, wherein an inertial sensor is added to the main control module for collecting inertial signals and sending the inertial signals to the main control module; when the main control module works in a training mode, the angle of an inertial signal is extracted and used as the characteristic of a certain reference gesture; when the main control module works in a recognition mode, firstly, angles of inertial signals collected by specific gestures are extracted, angle differences between the angles and all reference gestures with angle characteristics as characteristics are calculated respectively, minimum angle differences are screened out, if the minimum angle differences are smaller than a preset threshold value, the specific gestures are judged to be the reference gestures corresponding to the minimum angle differences, gesture recognition is successful, otherwise, gesture recognition based on the inertial signals fails, and gesture recognition is carried out based on surface electromyographic signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910812434.4A CN110618754B (en) | 2019-08-30 | 2019-08-30 | Surface electromyogram signal-based gesture recognition method and gesture recognition armband |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910812434.4A CN110618754B (en) | 2019-08-30 | 2019-08-30 | Surface electromyogram signal-based gesture recognition method and gesture recognition armband |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110618754A CN110618754A (en) | 2019-12-27 |
| CN110618754B true CN110618754B (en) | 2021-09-14 |
Family
ID=68922827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910812434.4A Active CN110618754B (en) | 2019-08-30 | 2019-08-30 | Surface electromyogram signal-based gesture recognition method and gesture recognition armband |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110618754B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113589920A (en) * | 2020-04-30 | 2021-11-02 | 北京海益同展信息科技有限公司 | Gesture recognition method, man-machine interaction method, device, equipment and storage medium |
| CN113688802B (en) * | 2021-10-22 | 2022-04-01 | 季华实验室 | Gesture recognition method, device and equipment based on electromyographic signals and storage medium |
| CN114931390B (en) * | 2022-05-06 | 2023-06-13 | 电子科技大学 | Muscle strength estimation method based on fatigue analysis |
| CN115114962A (en) * | 2022-07-19 | 2022-09-27 | 歌尔股份有限公司 | Control method and device based on surface electromyogram signal and wearable device |
| CN116019467A (en) * | 2023-03-28 | 2023-04-28 | 潍坊医学院附属医院 | Feature extraction method of facial nerve electromyographic signals |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484644A (en) * | 2014-11-06 | 2015-04-01 | 三星电子（中国）研发中心 | Gesture identification method and device |
| CN105807640A (en) * | 2014-12-30 | 2016-07-27 | 深圳Tcl新技术有限公司 | Terminal control method and terminal control system |
| CN106845348A (en) * | 2016-12-20 | 2017-06-13 | 南京信息工程大学 | A kind of gesture identification method based on arm surface electromyographic signal |
| CN108985157A (en) * | 2018-06-07 | 2018-12-11 | 北京邮电大学 | A kind of gesture identification method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10319473B2 (en) * | 2015-04-20 | 2019-06-11 | Kali Care, Inc. | Wearable system for healthcare management |
| CN107273798A (en) * | 2017-05-11 | 2017-10-20 | 华南理工大学 | A kind of gesture identification method based on surface electromyogram signal |
| CN108388348B (en) * | 2018-03-19 | 2020-11-24 | 浙江大学 | Myoelectric signal gesture recognition method based on deep learning and attention mechanism |
-
2019
- 2019-08-30 CN CN201910812434.4A patent/CN110618754B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104484644A (en) * | 2014-11-06 | 2015-04-01 | 三星电子（中国）研发中心 | Gesture identification method and device |
| CN105807640A (en) * | 2014-12-30 | 2016-07-27 | 深圳Tcl新技术有限公司 | Terminal control method and terminal control system |
| CN106845348A (en) * | 2016-12-20 | 2017-06-13 | 南京信息工程大学 | A kind of gesture identification method based on arm surface electromyographic signal |
| CN108985157A (en) * | 2018-06-07 | 2018-12-11 | 北京邮电大学 | A kind of gesture identification method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110618754A (en) | 2019-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110618754B (en) | Surface electromyogram signal-based gesture recognition method and gesture recognition armband | |
| EP3843617B1 (en) | Camera-guided interpretation of neuromuscular signals | |
| US11422623B2 (en) | Wrist worn computing device control systems and methods | |
| US9999391B2 (en) | Wearable electromyogram sensor system | |
| US11023045B2 (en) | System for recognizing user gestures according to mechanomyogram detected from user's wrist and method thereof | |
| CN112789577B (en) | Neuromuscular text input, writing and drawing in augmented reality systems | |
| US9367139B2 (en) | Systems, articles, and methods for gesture identification in wearable electromyography devices | |
| Yang et al. | A proportional pattern recognition control scheme for wearable a-mode ultrasound sensing | |
| EP2875778A1 (en) | Wearable mobile device and method of measuring biological signal with the same | |
| Zhang et al. | Recognizing hand gestures with pressure-sensor-based motion sensing | |
| CN103777752A (en) | Gesture recognition device based on arm muscle current detection and motion sensor | |
| CN105022471A (en) | Device and method for carrying out gesture recognition based on pressure sensor array | |
| US10521018B2 (en) | Human body-based interaction method and interaction apparatus | |
| Khodabandelou et al. | Attention-based gated recurrent unit for gesture recognition | |
| CN112566553A (en) | Real-time spike detection and identification | |
| CN103677265A (en) | Intelligent sensing glove and intelligent sensing method | |
| CN110522458A (en) | A kind of gait real-time identification method suitable for knee joint ectoskeleton | |
| KR20190098806A (en) | A smart hand device for gesture recognition and control method thereof | |
| Naik et al. | Classification of finger extension and flexion of EMG and Cyberglove data with modified ICA weight matrix | |
| Martínez-Villaseñor et al. | Deep learning for multimodal fall detection | |
| Chapman et al. | A wearable, open-source, lightweight forcemyography armband: on intuitive, robust muscle-machine interfaces | |
| US11705748B2 (en) | Wearable gesture recognition device for medical screening and associated operation method and system | |
| CN105718032A (en) | Spaced control autodyne aircraft | |
| Saggio et al. | Evaluation of an integrated sensory glove at decreasing joint flexion degree | |
| CN106020442A (en) | Sensing method for intelligent sensing glove |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |